Conference Agenda (All times are shown in Eastern Daylight Time)

With the ongoing advancement of big data and AI, automatic extraction of knowledge units from ancient Chinese texts (ACTs) has become a key focus in Chinese natural language processing. However, existing solutions often suffer from limited task coverage, inadequate quality evaluation, and challenges posed by the unique linguistic features of ACTs. These factors collectively hinder the broader adoption of intelligent ACT processing systems. To address these issues, we proposed a multi-task semantic annotation and generation system, named “KnowACT”, which includes a data loading layer, a task processing layer, and a result output layer. Our preliminary experiment has shown that when compared to other advanced annotation systems, KnowACT has significant advantages in the aspects of task functional integrity, annotation efficiency, and quality control of annotation texts. It is believed that KnowACT can promote the development of knowledge extraction technology and relevant systems for ACTs.

In this study we investigate the use of large language models (LLMs), specifically ChatGPT, for structured deductive qualitative coding. While most current research emphasizes inductive coding applications, we address the underexplored potential of LLMs to perform deductive classification tasks aligned with established human-coded schemes. Using the Comparative Agendas Project (CAP) Master Codebook, we classified U.S. Supreme Court case summaries into 21 major policy domains. We tested four intervention methods: zero-shot, few-shot, definition-based, and a novel Step-by-Step Task Decomposition strategy, across repeated samples. Performance was evaluated using standard classification metrics (accuracy, F1-score, Cohen’s κ, Krippendorff’s α), and construct validity was assessed using chi-squared tests and Cramér’s V. Chi-squared and effect size analyses confirmed that intervention strategies significantly influenced classification behavior, with Cramér’s V values ranging from 0.359 to 0.613, indicating moderate to strong shifts in classification patterns. The Step-by-Step Task Decomposition strategy achieved the strongest reliability (accuracy = 0.775, κ = 0.744, α = 0.746), achieving thresholds for substantial agreement. Despite the semantic ambiguity within case summaries, ChatGPT displayed stable agreement across samples, including high F1 scores in low-support subclasses. These findings demonstrate that with targeted, custom-tailored interventions LLMs can achieve reliability levels suitable for integration into rigorous qualitative coding workflows.

Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification and summarization tasks, but their capability to perform subject analysis is underexplored. Multi-label classification with traditional machine learning (ML) models has been used for subject analysis but struggles with unseen cases. LLMs offer an alternative but often over-generate and hallucinate. Therefore, we propose a hybrid framework that integrates embedding-based ML models with LLMs. This approach uses ML models to (1) predict the optimal number of LCSH labels to guide LLM predictions and (2) post-edit the predicted terms with actual LCSH terms to mitigate hallucinations. We experimented with LLMs and the hybrid framework to predict the subject terms of books using the Library of Congress Subject Headings (LCSH). Experiment results show that providing initial predictions to guide LLM generations and imposing post-edits result in more controlled and vocabulary-aligned outputs.

In this project, we semantically enriched and enhanced the metadata of long text documents, theses and dissertations, retrieved from the HathiTrust Digital Library in English published from 1920 to 2020 through a combination of manual efforts and large language models. This dataset provides a valuable resource for advancing research in areas such as computational social science, digital humanities, and information science. Our paper shows that enriching metadata using LLMs is particularly beneficial for digital repositories by introducing additional metadata access points that may not have originally been foreseen to accommodate various content types. This approach is particularly effective for repositories that have significant missing data in their existing metadata fields, enhancing search results, and improving the accessibility of the digital repository.